Demand Analysis under Price Rigidity and Endogenous Assortment: An Application to China's Tobacco Industry

TL;DR

This paper develops a demand model for China's tobacco industry that accounts for price rigidity and changing product assortments, revealing significant impacts on sales predictions and tax revenue estimations.

Contribution

It introduces a novel demand estimation approach incorporating endogenous assortments and price rigidity, improving accuracy over traditional models.

Findings

Consumers are more responsive to price changes than previously thought.

Neglecting assortment adjustments leads to underestimating sales declines and overestimating tax revenue.

The methodology extends to competitive markets and models with random coefficients.

Abstract

We observe nominal price rigidity in tobacco markets across China. The monopolistic seller responds by adjusting product assortments, which remain unobserved by the analyst. We develop and estimate a logit demand model that incorporates assortment discrimination and nominal price rigidity. We find that consumers are significantly more responsive to price changes than conventional models predict. Simulated tax increases reveal that neglecting the role of endogenous assortments results in underestimations of the decline in higher-tier product sales, incorrect directional predictions of lower-tier product sales, and overestimation of tax revenue by more than 50%. Finally, we extend our methodology to settings with competition and random coefficient models.